The Agent Skills Directory

[SAFE]: The skill is composed entirely of markdown documentation and reference guides. It does not contain any executable scripts, binary files, or automated commands.
[SAFE]: All UX reference content is bundled within the references/ directory. The skill specifically includes guardrails prohibiting live fetching of external data, which minimizes the risk of network-based attacks.
[SAFE]: No sensitive data access, hardcoded credentials, or network operations (such as curl or wget) are present in any of the skill's files.
[SAFE]: No obfuscation techniques, such as Base64 encoding or hidden Unicode characters, were detected in the instructions or reference data.
[SAFE]: The skill instructions define an audit workflow for the agent to evaluate user-provided UI code against UX laws. While this involves processing untrusted user data (Category 8 surface), the skill lacks the capabilities (like file writing or network access) to be exploited maliciously via indirect prompt injection.

audit-ux-laws